I really struggled when I attempted to conceptualize the evolution from data mining to topic modeling. I do understand that we have moved into the realm of probability, but I don’t really understand how LDA works. Jockers’ text was probably the most helpful but I was still confused. I did find an interesting article produced by the Department of Computer Science at Princeton that described probabilistic topic modeling. Their main goal is to “present a way of using topic models to help learn about and discover items in a corpus." They provided a visualization that I thought was quite intriguing because I was very interested in the subject matter. Here it is:
Comments (0)
You don't have permission to comment on this page.